Skip to contentSkip to conversation

Patch for tracing c states (power_end) on x86

PATCH Robert Schöne 4 participants 9 messages Feb 24, 2010 – Mar 11, 2010 x86

lore
Share & tools
lore
#0 lore raw

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Bye Robert

arch/x86/kernel/process.c +1 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,

unsigned long cx)

                if (!need_resched())
                        __mwait(ax, cx);
        }

+ trace_power_end((ax>>4)+1);
}

/* Default MONITOR/MWAIT with no hints, used for default C1 state */
@@ -467,6 +469,7 @@ static void mwait_idle(void)

                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();

}

#1 lore raw
Quoted 25 lines · Robert Schöne

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Bye Robert

arch/x86/kernel/process.c +1 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */

arch/x86/kernel/process.c void mwait_idle_with_hints(unsigned long ax, · line 456

Quoted 5 lines
arch/x86/kernel/process.c +1 -0
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);

The only argument of trace_power_end() is a dummy, so you can just pass 0 or 1 to the trace hook, actually better pass 0 to be consistent with other parts.

The dummy argument can't be eliminated, because the macros that automatically generates racing code have some limitations, and seems it's not so easy to get over.

Quoted 13 lines
arch/x86/kernel/process.c +0 -0
 }
 

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }
#2 lore raw

Hi,

I tried to pass 0 in "my" sleep routine "static void mwait_idle(void)" Which led to the following behaviour:
The event was reported on /sys/kernel/debug/tracing, but still not for sys_perf_open.
As 1 had been the argument which led to a working tracing, I assumed, that the argument should be the same as the 2nd arg of the last power_start event.
Since this argument had been 1 in my case, it worked for me. However, 0 did not.

Bye Robert

Am Mittwoch, den 24.02.2010, 16:36 +0800 schrieb Li Zefan:

Quoted 42 lines
Quoted 25 lines · Robert Schöne

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Bye Robert

arch/x86/kernel/process.c +1 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */

arch/x86/kernel/process.c void mwait_idle_with_hints(unsigned long ax, · line 456

Quoted 5 lines
arch/x86/kernel/process.c +1 -0
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);

The only argument of trace_power_end() is a dummy, so you can just pass 0 or 1 to the trace hook, actually better pass 0 to be consistent with other parts.

The dummy argument can't be eliminated, because the macros that automatically generates racing code have some limitations, and seems it's not so easy to get over.

Quoted 2 lines
arch/x86/kernel/process.c +0 -0
 }
 
Quoted 17 lines

arch/x86/kernel/process.c static void mwait_idle(void) · line 475

Quoted 11 lines

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

------------------------- Mail from Febr. 15th -------------------- Hi,
I have a question regarding the event "power/power_end". For the standard linux kernel (2.6.32.8), it's just not reported - neither for the /sys/kernel/debug/tracing nor for the sys_perf_open approach.

System:
Intel Core 2 Quad,
Kernel 2.6.32.8,
for sys_perf_open:always using sampling counters, (Kernel 2.6.33-rcX should show the same behavior)

After finding "my" c-state procedure in arch/x86/kernel/process.c (which was "static void mwait_idle(void)" btw), I added a trace_power_end call on the correct line:
...

                else
                        local_irq_enable();
        } else
...
->
...
                else
                        local_irq_enable();
                trace_power_end(0);
        } else

...
Now the event was reported on /sys/kernel/debug/tracing, but still not for sys_perf_open.

Then I had the idea, that trace_power_end's argument should be the same as the 2nd argument of the previous power_start.

That worked.

However, things to be done are: add trace_power_end's to some process.c's procedures.

Bye Robert

-------------------------End of Mail of Febr. 15th --------------------

#3 lore raw
Quoted 2 lines · Robert Schöne

Hi,

Please don't top posting. :)

Quoted 4 lines

I tried to pass 0 in "my" sleep routine "static void mwait_idle(void)" Which led to the following behaviour:
The event was reported on /sys/kernel/debug/tracing, but still not for sys_perf_open.

The event was not reported by sys_perf_open()? Could you be more elaborate on this? Because I don't get you here.

Quoted 116 lines

As 1 had been the argument which led to a working tracing, I assumed, that the argument should be the same as the 2nd arg of the last power_start event.
Since this argument had been 1 in my case, it worked for me. However, 0 did not.

Bye Robert

Am Mittwoch, den 24.02.2010, 16:36 +0800 schrieb Li Zefan:

Quoted 41 lines
Quoted 25 lines · Robert Schöne

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Bye Robert

arch/x86/kernel/process.c +1 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */

arch/x86/kernel/process.c void mwait_idle_with_hints(unsigned long ax, · line 456

Quoted 5 lines
arch/x86/kernel/process.c +1 -0
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);

The only argument of trace_power_end() is a dummy, so you can just pass 0 or 1 to the trace hook, actually better pass 0 to be consistent with other parts.

The dummy argument can't be eliminated, because the macros that automatically generates racing code have some limitations, and seems it's not so easy to get over.

Quoted 2 lines
arch/x86/kernel/process.c +0 -0
 }
 
Quoted 17 lines

arch/x86/kernel/process.c static void mwait_idle(void) · line 475

Quoted 11 lines

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

------------------------- Mail from Febr. 15th -------------------- Hi,
I have a question regarding the event "power/power_end". For the standard linux kernel (2.6.32.8), it's just not reported - neither for the /sys/kernel/debug/tracing nor for the sys_perf_open approach.

System:
Intel Core 2 Quad,
Kernel 2.6.32.8,
for sys_perf_open:always using sampling counters, (Kernel 2.6.33-rcX should show the same behavior)

After finding "my" c-state procedure in arch/x86/kernel/process.c (which was "static void mwait_idle(void)" btw), I added a trace_power_end call on the correct line:
...

                else
                        local_irq_enable();
        } else
...
->
...
                else
                        local_irq_enable();
                trace_power_end(0);
        } else

...
Now the event was reported on /sys/kernel/debug/tracing, but still not for sys_perf_open.

Then I had the idea, that trace_power_end's argument should be the same as the 2nd argument of the previous power_start.

That worked.

However, things to be done are: add trace_power_end's to some process.c's procedures.

Bye Robert

-------------------------End of Mail of Febr. 15th --------------------

#4 lore raw

I forgot to mention that I appended my original mail at the bottom of my previous one.
Here it is:

Quoted 6 lines

------------------------- Mail from Febr. 15th --------------------

Quoted 5 lines

Hi,
I have a question regarding the event "power/power_end". For the standard linux kernel (2.6.32.8), it's just not reported - neither for the /sys/kernel/debug/tracing nor for the sys_perf_open approach.

Reported means here: sampling events were not generated/there were no entries in debug/tracing.

Quoted 30 lines
Quoted 30 lines

System:
Intel Core 2 Quad,
Kernel 2.6.32.8,
for sys_perf_open:always using sampling counters, (Kernel 2.6.33-rcX should show the same behavior)

After finding "my" c-state procedure in arch/x86/kernel/process.c (which was "static void mwait_idle(void)" btw), I added a trace_power_end call on the correct line:
...

                else
                        local_irq_enable();
        } else
...
->
...
                else
                        local_irq_enable();
                trace_power_end(0);
        } else

...
Now the event was reported on /sys/kernel/debug/tracing, but still not for sys_perf_open.

Then I had the idea, that trace_power_end's argument should be the same as the 2nd argument of the previous power_start.

That worked.

Quoted 7 lines
Quoted 7 lines

However, things to be done are: add trace_power_end's to some process.c's procedures.

Bye Robert

-------------------------End of Mail of Febr. 15th --------------------

Am Mittwoch, den 24.02.2010, 17:00 +0800 schrieb Li Zefan:

Quoted 94 lines
Quoted 2 lines · Robert Schöne

Hi,

Please don't top posting. :)

Quoted 4 lines

I tried to pass 0 in "my" sleep routine "static void mwait_idle(void)" Which led to the following behaviour:
The event was reported on /sys/kernel/debug/tracing, but still not for sys_perf_open.

The event was not reported by sys_perf_open()? Could you be more elaborate on this? Because I don't get you here.

Quoted 6 lines

As 1 had been the argument which led to a working tracing, I assumed, that the argument should be the same as the 2nd arg of the last power_start event.
Since this argument had been 1 in my case, it worked for me. However, 0 did not.

Quoted 68 lines

Bye Robert

Am Mittwoch, den 24.02.2010, 16:36 +0800 schrieb Li Zefan:

Quoted 58 lines
Quoted 25 lines · Robert Schöne

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Bye Robert

arch/x86/kernel/process.c +1 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */

arch/x86/kernel/process.c void mwait_idle_with_hints(unsigned long ax, · line 456

Quoted 5 lines
arch/x86/kernel/process.c +1 -0
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);

The only argument of trace_power_end() is a dummy, so you can just pass 0 or 1 to the trace hook, actually better pass 0 to be consistent with other parts.

The dummy argument can't be eliminated, because the macros that automatically generates racing code have some limitations, and seems it's not so easy to get over.

arch/x86/kernel/process.c static void mwait_idle(void) · line 475

Quoted 13 lines
arch/x86/kernel/process.c +0 -0
 }
 

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Signature · 7 lines
Robert Schoene
Technische Universitaet Dresden
Zentrum fuer Informationsdienste und Hochleistungsrechnen
01062 Dresden

Tel.: (0351) 463-42483, Fax: (0351) 463-37773
E-Mail: [email protected]
#5 lore raw
In reply to Robert Schöne
Quoted 8 lines · Robert Schöne

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Arjan, any comments?, you seem skilled with this power stuff ;-)

Quoted 30 lines
arch/x86/kernel/process.c +2 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);
 }
 

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }
#6 lore raw

Did anyone look at the problem described and checked the patch? I still received no reply.

Am Donnerstag, den 25.02.2010, 13:52 +0100 schrieb Peter Zijlstra:

Quoted 50 lines · Robert Schöne
Quoted 8 lines

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Arjan, any comments?, you seem skilled with this power stuff ;-)

Quoted 23 lines
arch/x86/kernel/process.c +2 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);
 }
 

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c static void mwait_idle(void) · line 475

Quoted 7 lines
arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Signature · 7 lines
Robert Schoene
Technische Universitaet Dresden
Zentrum fuer Informationsdienste und Hochleistungsrechnen
01062 Dresden

Tel.: (0351) 463-42483, Fax: (0351) 463-37773
E-Mail: [email protected]
#7 lore raw
Quoted 2 lines · Robert Schöne

Did anyone look at the problem described and checked the patch? I still received no reply.

Ingo, how about applying it and letting people complain when they don't agree? :-)

Quoted 44 lines

Am Donnerstag, den 25.02.2010, 13:52 +0100 schrieb Peter Zijlstra:

Quoted 43 lines · Robert Schöne
Quoted 8 lines

Hello,

Since noone replied to my last mail (Febr. 15th, 11:42), describing the way to fix the missing c-state tracing, here's a patch. Maybe its easier that way.

(I used the perf-fixes-for-linus git tree to obtain a more-then-up-to-date version)

Arjan, any comments?, you seem skilled with this power stuff ;-)

Quoted 30 lines
arch/x86/kernel/process.c +2 -0
index 02d6780..b1cfb88 100644
@@ -384,6 +384,7 @@ void default_idle(void)
                else
                        local_irq_enable();
                current_thread_info()->status |= TS_POLLING;
+               trace_power_end(1);
        } else {
                local_irq_enable();
                /* loop is done by the caller */
@@ -451,6 +452,7 @@ void mwait_idle_with_hints(unsigned long ax,
 unsigned long cx)
                if (!need_resched())
                        __mwait(ax, cx);
        }
+       trace_power_end((ax>>4)+1);
 }
 

/* Default MONITOR/MWAIT with no hints, used for default C1 state */

arch/x86/kernel/process.c +1 -0
@@ -467,6 +469,7 @@ static void mwait_idle(void)
                        __sti_mwait(0, 0);
                else
                        local_irq_enable();
+               trace_power_end(1);
        } else
                local_irq_enable();
 }
#8 lore raw
Quoted 6 lines · Peter Zijlstra
Quoted 2 lines · Robert Sch??ne

Did anyone look at the problem described and checked the patch? I still received no reply.

Ingo, how about applying it and letting people complain when they don't agree? :-)

We can do that. Robert, mind sending the patch with a changelog and with your Signed-off-by and with Peter's Acked-by?

Thanks,

Ingo